Related papers: SAIL: Self-supervised Albedo Estimation from Real …
Although recently several foundation models for satellite remote sensing imagery have been proposed, they fail to address major challenges of real/operational applications. Indeed, embeddings that don't take into account the spectral,…
Although supervised learning has enabled high performance for image segmentation, it requires a large amount of labeled training data, which can be difficult to obtain in the medical imaging field. Self-supervised learning (SSL) methods…
We present color sails, a discrete-continuous color gamut representation that extends the color gradient analogy to three dimensions and allows interactive control of the color blending behavior. Our representation models a wide variety of…
Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent…
How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In…
Image deblurring techniques play important roles in many image processing applications. As the blur varies spatially across the image plane, it calls for robust and effective methods to deal with the spatially-variant blur problem. In this…
Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data…
Semantic segmentation of outdoor scenes is problematic when there are variations in imaging conditions. It is known that albedo (reflectance) is invariant to all kinds of illumination effects. Thus, using reflectance images for semantic…
In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…
Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce…
Inferring the depth of images is a fundamental inverse problem within the field of Computer Vision since depth information is obtained through 2D images, which can be generated from infinite possibilities of observed real scenes. Benefiting…
In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real-world degradations with different degrees or types. In…
Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images from the seed noise? This is known as the…
Image-to-image relighting requires representations that disentangle scene properties from illumination. Recent methods rely on latent intrinsic representations but remain under-constrained and often fail on challenging materials such as…
One major branch of saliency object detection methods is diffusion-based which construct a graph model on a given image and diffuse seed saliency values to the whole graph by a diffusion matrix. While their performance is sensitive to…
We consider the non-Lambertian object intrinsic problem of recovering diffuse albedo, shading, and specular highlights from a single image of an object. We build a large-scale object intrinsics database based on existing 3D models in the…
Vessel segmentation in medical images is one of the important tasks in the diagnosis of vascular diseases and therapy planning. Although learning-based segmentation approaches have been extensively studied, a large amount of ground-truth…
Undoing the image formation process and therefore decomposing appearance into its intrinsic properties is a challenging task due to the under-constraint nature of this inverse problem. While significant progress has been made on inferring…
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by deep learning-based solutions, where many…
In this paper, we propose a novel label propagation based method for saliency detection. A key observation is that saliency in an image can be estimated by propagating the labels extracted from the most certain background and object…